RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929382457606144 |
|---|---|
| author | Yeh, Chin-Chia Michael Fan, Yujie Dai, Xin Saini, Uday Singh Lai, Vivian Aboagye, Prince Osei Wang, Junpeng Chen, Huiyuan Zheng, Yan Zhuang, Zhongfang Wang, Liang Zhang, Wei |
| author_facet | Yeh, Chin-Chia Michael Fan, Yujie Dai, Xin Saini, Uday Singh Lai, Vivian Aboagye, Prince Osei Wang, Junpeng Chen, Huiyuan Zheng, Yan Zhuang, Zhongfang Wang, Liang Zhang, Wei |
| contents | Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting models, i.e., models that do not leverage the spatial relationships among the nodes. We propose a all-Multi-Layer Perceptron (all-MLP) time series forecasting architecture called RPMixer. The all-MLP architecture was chosen due to its recent success in time series forecasting benchmarks. Furthermore, our method capitalizes on the ensemble-like behavior of deep neural networks, where each individual block within the network behaves like a base learner in an ensemble model, particularly when identity mapping residual connections are incorporated. By integrating random projection layers into our model, we increase the diversity among the blocks' outputs, thereby improving the overall performance of the network. Extensive experiments conducted on the largest spatial-temporal forecasting benchmark datasets demonstrate that the proposed method outperforms alternative methods, including both spatial-temporal graph models and general forecasting models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10487 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data Yeh, Chin-Chia Michael Fan, Yujie Dai, Xin Saini, Uday Singh Lai, Vivian Aboagye, Prince Osei Wang, Junpeng Chen, Huiyuan Zheng, Yan Zhuang, Zhongfang Wang, Liang Zhang, Wei Machine Learning Artificial Intelligence Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting models, i.e., models that do not leverage the spatial relationships among the nodes. We propose a all-Multi-Layer Perceptron (all-MLP) time series forecasting architecture called RPMixer. The all-MLP architecture was chosen due to its recent success in time series forecasting benchmarks. Furthermore, our method capitalizes on the ensemble-like behavior of deep neural networks, where each individual block within the network behaves like a base learner in an ensemble model, particularly when identity mapping residual connections are incorporated. By integrating random projection layers into our model, we increase the diversity among the blocks' outputs, thereby improving the overall performance of the network. Extensive experiments conducted on the largest spatial-temporal forecasting benchmark datasets demonstrate that the proposed method outperforms alternative methods, including both spatial-temporal graph models and general forecasting models. |
| title | RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.10487 |